You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Complex interpretation of Tensorflow Probability tensor_coercible object
I have a tensorflow model (keras sequential) that ends with a Tensorflow Probability (TFP) mixture layer. My goal is to fit this network with a custom loss function. The unexpected behaviour is the following:
When I pass a custom loss like this:
def wass_loss(y_true, y_pred):
print(type(y_pred))
print(type(y_true))
# Do multiple 'tf' operations, one of them, sample the _TensorCoercible
return ...
Which is unexpected, I would expect the Tensor Coercible from TFP to still be a Tensor Coercible. Yet, looks like that after the new loss (which might be computed first), it is already a Symbolic Tensor Why is it happening? What am I missing?
Thanks a lot!
The text was updated successfully, but these errors were encountered:
Complex interpretation of Tensorflow Probability tensor_coercible object
I have a tensorflow model (keras sequential) that ends with a Tensorflow Probability (TFP) mixture layer. My goal is to fit this network with a custom loss function. The unexpected behaviour is the following:
When I pass a custom loss like this:
It prints:
Intepreting each argument correctly and results are ok /coherent.
Now, when I compile this same network with another loss func. and use the
wass_loss
above as metric.I get:
Which is unexpected, I would expect the Tensor Coercible from TFP to still be a Tensor Coercible. Yet, looks like that after the new loss (which might be computed first), it is already a Symbolic Tensor Why is it happening? What am I missing?
Thanks a lot!
The text was updated successfully, but these errors were encountered: